Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7686
    Prev
    Next
    INDEX
    Explanations

    absence or negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Incomplete
    -0.88
     menina
    -0.81
    也不能
    -0.79
     incomplete
    -0.73
     Botan
    -0.73
    ieux
    -0.71
     uncut
    -0.69
     fantastisk
    -0.68
     incluindo
    -0.68
    tomie
    -0.68
    POSITIVE LOGITS
     нет
    3.47
     absence
    3.38
     немає
    3.14
    ไม่มี
    3.03
     absent
    2.92
     отсут
    2.86
     없
    2.58
    不存在
    2.52
     Absence
    2.50
     אין
    2.41
    Activations Density 0.028%

    No Known Activations